Birch-san

# Contains MIT-licensed code from wandb
# https://github.com/wandb/wandb/blob/main/LICENSE
# This gist is MIT-licensed (Copyright Alex Birch)

from torch import Tensor, FloatTensor
from torch.nn import Module
from torch.utils.hooks import RemovableHandle
import torch
from typing import List, Callable, Dict, Sequence, Optional, Tuple, Any
from wandb.wandb_torch import log_track_init, log_track_update

madebyollin

Objective

Informal (vibes-based) evaluation of the following vision-language-model captioners:

• Florence-2-base-ft
• CogVLM2
• BLIP-2
• MoonDream2
• Share-Captioner
• Florence-2-SD3-Captioner

cloneofsimo

import torch


class TwoDimRotary(torch.nn.Module):
    def __init__(self, dim, base=100, h = 128, w = 128):
        super().__init__()
        self.inv_freq = 1.0 / (base ** (torch.arange(0, dim, 2).float() / (dim)))
        self.h = h
        self.w = w